首页>
外国专利>
Effective Doubly-Accelerated Distributed Asynchronous Strategy for General Convex Optimization Problem
Effective Doubly-Accelerated Distributed Asynchronous Strategy for General Convex Optimization Problem
展开▼
机译:一般凸优化问题的有效双加速分布式异步策略
展开▼
页面导航
摘要
著录项
相似文献
摘要
#$%^&*AU2020100180A420200312.pdf#####Abstract With advent of the large-scale network or data era, traditional synchronous algorithms, due to the requirement of the clock synchronization, is not suitable for handling large-scale network tasks. In view of this, this patent presents an effective doubly-accelerated distributed asynchronous algorithm based on heavy-ball method and Nesterov gradient method for solving general convex optimization problems, which are defined in a fixed directed multi-node network system. The algorithm mainly comprises six stages including variable initialization; picking delay value and activated node; eliminating outdated information; computing gradient; exchanging information; updating variable. The algorithm set forth in the present invention adopts a general asynchronous scheme, where agents can communicate with their in-neighbors at any time without any coordination or scheduling and perform their local computations by using outdated information from their in-neighbors. Therefore, the algorithm highly reduces idle time of communication links, mitigates congestion of communication and memory access, saves power, and has more fault-tolerant and robust. The present invention has broad application in large-scale machine learning and network information processing.Start Select the global objective function Each node initializes local variables Each node set k-0 and and maximum number of iteration, kmax N .k Y Compute system parameters Pick delay value dk Eliminate the old variables Select a step size and a momentum parameter according to the computing parameters Each activated node updates the variables and computes the gradient Each activated node sends variables to its out-neighbor nodes Each activated node sets k-k+ k k x?N Y End Fig. 4
展开▼
机译:#$%^&* AU2020100180A420200312.pdf #####抽象随着大规模网络或数据时代的到来,传统的同步算法应运而生。对时钟同步的要求,不适合处理大型网络任务。有鉴于此,该专利提出了一种有效的双加速分布式异步重球法和Nesterov梯度法的通用凸算法优化问题,在固定的定向多节点网络系统中定义。的该算法主要包括变量初始化六个阶段。拣货延迟值和激活节点;消除过时的信息;计算梯度;交流信息;更新变量。本发明中提出的算法采用通用异步方案,代理可以在没有协调的情况下随时与邻居进行通讯或调度并通过使用来自他们的过时信息来执行其本地计算邻居。因此,该算法大大减少了通信链路的空闲时间,减轻了通信和内存访问的拥塞,节省功率,并具有更多的容错能力和强大的。本发明在大规模机器学习和网络中具有广泛的应用。信息处理。开始选择全局目标函数每个节点初始化局部变量每个节点设置k-0和和最大数量迭代,kmax。ÿ计算系统参数拾取延迟值dk消除旧变数选择一个步长和一个动量参数根据计算参数每个激活的节点更新变量并计算梯度每个激活的节点向其发送变量邻居节点每个激活的节点集k +k> k x?Nÿ结束图4
展开▼